CN106250839A - A kind of iris image perspective correction method, device and mobile terminal - Google Patents
A kind of iris image perspective correction method, device and mobile terminal Download PDFInfo
- Publication number
- CN106250839A CN106250839A CN201610602917.8A CN201610602917A CN106250839A CN 106250839 A CN106250839 A CN 106250839A CN 201610602917 A CN201610602917 A CN 201610602917A CN 106250839 A CN106250839 A CN 106250839A
- Authority
- CN
- China
- Prior art keywords
- iris image
- image
- iris
- coordinate
- human eye
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
Abstract
The invention discloses a kind of iris image perspective correction method, be suitable to perform in the terminal, the method includes: obtain the original iris image of user to be identified；Calculate the three dimensional space coordinate p of every bit in described original iris images＇；The angle theta of the direction of visual lines of human eye and horizontal direction when positional information calculation according to described human eye iris and original iris image thereof obtains original iris image；The transformation matrix of described iris image perspective correction is built according to described angle, θ；According to the described transformation matrix three dimensional space coordinate p to described original iris images＇ carries out coordinate transform, the three dimensional space coordinate p of the iris image after being correcteds.The invention also discloses a kind of iris image perspective correction device and mobile terminal.
Description
Technical field
The present invention relates to image procossing and area of pattern recognition, more particularly, to a kind of iris image perspective correction side
Method, device and mobile terminal.
Background technology
Along with intelligent mobile terminal and the fast development of network technology, people's safety to information especially personal information
Improve constantly with stability requirement, utilize people's unique physiological feature inherently or behavior characteristics to carry out the application of authentication
More and more extensive.Wherein, in addition to the technology such as fingerprint recognition, recognition of face, the iris identification skill of an other more safety
Art is also increasingly subject to the favor of people.And, along with the continuous progress of science and technology, iris authentication system is gradually applied to mobile phone, puts down
In the electronic equipment small and exquisite, frivolous, portative such as plate and notebook.
Generally, when user uses mobile phone to carry out iris identification, in order to see the eye image presented on the display screen,
Need to make to produce between eyes and mobile phone an angle.This angle makes the profile of iris image become oval from circle.
Due to blocking of eyelid, the profile of iris image is typically incomplete circle or ellipse.Existing Algorithm of Iris Recognition can be reliable
Detect incomplete circle efficiently, but can not reliably and effectively detect incomplete ellipse.
The automatic distortions correction that the current method that iris image carries out perspective correction has distinguished point based to detect, the party
Method is it needs to be determined that the positional information of characteristic point or have reference picture.That is, the stack features detected in a reference image is contrasted
Point and another stack features point detected in present image, estimate the rotation between photographing unit and target and translation, the most right
Present image converts, and obtains the characteristic point position consistent with reference picture.Obviously, this method requires to hold in the picture
Abundant and sufficiently stable characteristic point easily detected, and illumination condition and interference are the most sensitive to external world.For different
The face area of people, it is difficult to reliably obtain the characteristic point of fixed position, and amount of calculation is relatively big, is not suitable for mobile terminal
The requirement of real-time of iris application.
It is, therefore, desirable to provide the quick approximation method of a kind of this metamorphopsic distortion of automatic correction, obtain one and circular lose
The least iris image, reduces the difficulty of subsequent treatment.
Summary of the invention
To this end, the present invention provides a kind of iris image perspective correction method, device and mobile terminal, solve trying hard to or
At least alleviate at least one problem existed above.
According to an aspect of the present invention, a kind of iris image perspective correction method, be suitable to perform in the terminal, should
Method includes: obtain the original iris image of user to be identified；Calculate the three dimensional space coordinate of every bit in original iris image
ps＇；The sight line side of human eye when positional information calculation according to human eye iris and original iris image thereof obtains original iris image
To the angle theta with horizontal direction；The transformation matrix of iris image perspective correction is built according to angle, θ；According to transformation matrix to former
The three dimensional space coordinate p of beginning iris images＇ carries out coordinate transform, the three dimensional space coordinate p of the iris image after being correcteds。
Alternatively, in the iris image perspective correction method according to the present invention, also include: build described according to angle, θ
The spin matrix R and R ＇ of camera lens and former world coordinate system, wherein sets the initial point of former world coordinate system as incident light axis and people
The intersection point of eye iris place plane, and have two coordinate axess to lay respectively at gravity and horizontal direction.
Alternatively, in the iris image perspective correction method according to the present invention, ps=CR [(R ＇)-1C-1ps＇+c ＇-c],
Wherein, C is the camera matrix through coefficient adjustment, is suitable to the pixel unit in image is converted to long measure；C and c ＇ is respectively
It is that the optical center of camera rotates θ angle relative to former world coordinate system and former world coordinate system around the axle of non-gravity and horizontal direction
After the coordinate of new coordinate system.
Alternatively, in the iris image perspective correction method according to the present invention,Wherein,It is the depth information of every bit in original iris image, is suitable to be calculated according to anglec of rotation θ and object distance u.
Alternatively, in the iris image perspective correction method according to the present invention, R is unit matrix,
Alternatively, in the iris image perspective correction method according to the present invention, the computing formula of angle, θ is:
Wherein, u is object distance, and v is image distance, and h is that the central point of imageing sensor mid-infrared imaging region passes to described image
The distance of sensor central point, H is the central point distance to described incident light axis of described human eye iris, and a is described mobile terminal
Screen in image display area to the distance of described image sensor center point.
Alternatively, in the iris image perspective correction method according to the present invention, c=[cx,cy,cz]T, c ＇=[cx＇,
cy＇, cz＇]T, wherein, T is matrix transpose, c and c ＇ is suitable to by angle theta, object distance u and the central point of human eye iris and incident illumination
Distance H of axle is calculated.
Alternatively, in the iris image perspective correction method according to the present invention, cx=cy=0, cz=-u, cx'=0,
Alternatively, in the iris image perspective correction method according to the present invention, camera matrix
Focal length (f including two change in coordinate axis directionx, fy) and photocentre coordinate (cx, cy)。
Alternatively, in the iris image perspective correction method according to the present invention, also include: according to eyes location algorithm from
Imaging region determines position of human eye, and its position coordinates is scaled long measure from pixel unit；And by after correction
Long measure in iris image coordinate is scaled pixel unit, and the iris image that remaps.
According to another aspect of the present invention, it is provided that a kind of iris image perspective correction device, be suitable to reside in movement
In terminal, this device includes: image acquisition unit, is suitable to obtain the original iris image of user to be identified；Coordinate calculating unit,
Be suitable to calculate the three dimensional space coordinate p of every bit in original iris images＇；Angle calculation unit, be suitable to according to human eye iris and
The angle of the direction of visual lines of human eye and horizontal direction when the positional information calculation of its original iris image obtains original iris image
θ；Matrix construction unit, is suitable to build the transformation matrix of iris image perspective correction according to angle, θ；Coordinate transformation unit, is suitable to
According to the transformation matrix three dimensional space coordinate p to original iris images＇ carries out coordinate transform, the iris image after being corrected
Three dimensional space coordinate ps。
Alternatively, in the iris image perspective correction device according to the present invention, matrix construction unit is further adapted for according to angle
Degree θ builds camera lens and the spin matrix R and R ＇ of former world coordinate system, wherein sets the initial point of former world coordinate system as incident illumination
Axle and the intersection point of human eye iris place plane, and have two coordinate axess to lay respectively at gravity and horizontal direction.
Alternatively, in the iris image perspective correction device according to the present invention, ps=CR [(R ＇)-1C-1ps＇+c ＇-c],
Wherein, C is the camera matrix through coefficient adjustment, is suitable to the pixel unit in image is converted to long measure；C and c ＇ is respectively
It is that the optical center of camera rotates θ angle relative to former world coordinate system and former world coordinate system around the axle of non-gravity and horizontal direction
After the coordinate of new coordinate system.
Alternatively, in the iris image perspective correction device according to the present invention,Wherein,It is the depth information of every bit in original iris image, is suitable to be calculated according to anglec of rotation θ and object distance u.
Alternatively, in the iris image perspective correction device according to the present invention, R is unit matrix,
Alternatively, in the iris image perspective correction device according to the present invention, the computing formula of angle, θ is:
Wherein, u is object distance, and v is image distance, and h is that the central point of imageing sensor mid-infrared imaging region passes to described image
The distance of sensor central point, H is the central point distance to described incident light axis of described human eye iris, and a is described mobile terminal
Screen in image display area to the distance of described image sensor center point.
Alternatively, in the iris image perspective correction device according to the present invention, c=[cx,cy,cz]T, c ＇=[cx＇,
cy＇, cz＇]T, wherein, T is matrix transpose, c and c ＇ is suitable to by angle theta, object distance u and the central point of human eye iris and incident illumination
Distance H of axle is calculated.
Alternatively, in the iris image perspective correction device according to the present invention, cx=cy=0, cz=-u, cx＇=0,
Alternatively, in the iris image perspective correction device according to the present invention, camera matrix
Focal length (f including two change in coordinate axis directionx, fy) and photocentre coordinate (cx, cy)。
Alternatively, in the iris image perspective correction device according to the present invention, also include unit conversion unit, be suitable to root
From imaging region, determine position of human eye according to eyes location algorithm, and its position coordinates is scaled length list from pixel unit
Position；And the long measure in the iris image coordinate after being suitable to correction is scaled pixel unit, and the iris figure that remaps
Picture.
According to a further aspect of the invention, it is provided that a kind of mobile terminal, have an X-rayed including iris image as above
Correcting unit.
Alternatively, according in the mobile terminal of the present invention, also include and described iris image perspective correction device phase coupling
The complex imaging system connect, this complex imaging system includes: lens assembly, including the optical lens of fixed focal length；Filter set
Part, the near-infrared passed through including the visible band pass filter allowing the light of visible light wave range to pass through and permission near infrared light wave band
Light bandpass region；And imageing sensor, including visual light imaging region, near infrared light imaging region and the two region it
Between transitional region, wherein, it is seen that photoimaging area under visual light imaging pattern to by visible band pass filter can
See that light carries out imaging, and near infrared light imaging region under near infrared light imaging pattern to by near infrared light bandpass filter
Near infrared light carry out imaging.
According to technical scheme, by human eye sight during iris identification relative to the rotation of mobile terminal or mobile whole
The rotation relative to human eye sight, the unified human eye sight that is equivalent to is held to rotate θ angle, gravity side in world coordinate system from horizontal direction
To axle also rotate θ angle.This programme, according to display position, image space and the relation of sight angle of human eye iris, calculates
The mobile terminal angle of inclination when carrying out iris identification, and the change of iris image perspective correction is built by calculating angle of inclination
Change matrix.According to transformation matrix, human eye iris is carried out against perspective projection under the coordinate system rotated, then at the coordinate not rotated
Carry out perspective projection under system, can solve because during iris identification, the screen out of plumb of the direction of visual lines of human eye and mobile terminal is led
The problem of the iris image deformation caused.I.e. by estimating the angle of human eye and imaging device, it is achieved the quick correction of distorted image
Conversion, is modified to closer to circle by oval iris image, it is simple to follow-up identifying processing, improves the accurate of iris identification
Degree.
Accompanying drawing explanation
In order to realize above-mentioned and relevant purpose, herein in conjunction with explained below and accompanying drawing, some illustrative side is described
Face, these aspects indicate can to put into practice the various modes of principles disclosed herein, and all aspects and equivalence aspect
It is intended to fall under in the range of theme required for protection.By reading in conjunction with the accompanying detailed description below, the disclosure above-mentioned
And other purpose, feature and advantage will be apparent from.Throughout the disclosure, identical reference generally refers to identical
Parts or element.
Fig. 1 shows the structured flowchart of mobile terminal 100 according to an embodiment of the invention；
Fig. 2 shows the structural frames of the complex imaging system 200 of mobile terminal 100 according to an embodiment of the invention
Figure；
Fig. 3 shows use mobile terminal collection auto heterodyne image and the schematic diagram of iris identification image；
Fig. 4 shows that human eye iris image space under different sight angle is with aobvious according to an embodiment of the invention
Show the schematic diagram of position；
Fig. 5 shows the flow chart of iris image perspective correction method 500 according to an embodiment of the invention；
Fig. 6 A and 6B respectively illustrates the image schematic diagram carried out according to an embodiment of the invention before and after perspective correction；
Fig. 7 shows the structured flowchart of iris image perspective correction device 700 according to an embodiment of the invention.
Detailed description of the invention
It is more fully described the exemplary embodiment of the disclosure below with reference to accompanying drawings.Although accompanying drawing shows the disclosure
Exemplary embodiment, it being understood, however, that may be realized in various forms the disclosure and should be by embodiments set forth here
Limited.On the contrary, it is provided that these embodiments are able to be best understood from the disclosure, and can be by the scope of the present disclosure
Complete conveys to those skilled in the art.
Fig. 1 is mobile terminal 100 organigram according to an embodiment of the invention.As described in Fig. 1, mobile
Terminal 100 includes: memory interface 102, one or more data processor, image processor and/or CPU
104, and peripheral interface 106.Memory interface 102, one or more processor 104 and/or peripheral interface 106 both can be
Discrete component, it is also possible to be integrated in one or more integrated circuit.In the mobile terminal 100, various elements can be by one
Bar or a plurality of communication bus or holding wire couple.Sensor, equipment and subsystem are alternatively coupled to peripheral interface 106, in order to
Help realizes several functions.Such as, motion sensor 110, optical sensor 112 and range sensor 114 are alternatively coupled to periphery
Interface 106, facilitating orientation, illuminates and the function such as range finding.Other sensors 116 are equally connected with peripheral interface 106, example
Such as alignment system (such as GPS), temperature sensor, biometric sensor or other sensor devices, thus can help
Help and implement relevant function.
Camera sub-system 120 and optical pickocff 122 may be used for the camera of convenient such as recording photograph and video clipping
The realization of function, wherein said camera sub-system and optical pickocff can be such as charge-coupled image sensor (CCD) or complementary gold
Belong to oxide semiconductor (CMOS) optical pickocff.Can help to realize by one or more radio communication subsystem 124
Communication function, wherein radio communication subsystem can include radio-frequency transmitter and transmitter and/or light (the most infrared) receiver
And transmitter.The particular design of radio communication subsystem 124 and embodiment can depend on that mobile terminal 100 is supported
Individual or multiple communication networks.Such as, mobile terminal 100 can include being designed to support GSM network, GPRS network, EDGE net
The communication subsystem 124 of network, Wi-Fi or WiMax network and BlueboothTM network.Audio subsystem 126 can with raise one's voice
Device 128 and mike 130 are coupled, in order to help the function implementing to enable voice, such as speech recognition, speech reproduction, number
Word record and telephony feature.
I/O subsystem 140 can include touch screen controller 142 and/or other input controllers 144 one or more.
Touch screen controller 142 is alternatively coupled to touch screen 146.For example, this touch screen 146 and touch screen controller 142 are permissible
Use any one of multiple touch-sensing technology to detect the contact and movement or time-out carried out therewith, wherein sense skill
Art is including, but not limited to capacitive character, resistive, infrared and surface acoustic wave technique.Other input controllers 144 one or more
Be alternatively coupled to other input/control devicess 148, the most one or more buttons, rocker switch, thumb wheel, infrared port,
The pointer device of USB port and/or instruction pen etc.The one or more button (not shown) can include for controlling
Speaker 128 and/or the up/down button of mike 130 volume.
Memory interface 102 can be coupled with memorizer 150.This memorizer 150 can include that high random access is deposited
Reservoir and/or nonvolatile memory, the most one or more disk storage equipment, one or more optical storage apparatus, and/
Or flash memories (such as NAND, NOR).Memorizer 150 can store operating system 152, such as Android, IOS or
The operating system of Windows Phone etc.This operating system 152 can include for processing basic system services and execution
Depend on the instruction of the task of hardware.Memorizer 150 can also store application 154.These apply when operation, can be from memorizer
150 are loaded on processor 104, and run on the operating system run by processor 104, and utilize operating system
And the interface that bottom hardware provides realizes the desired function of various user, such as instant messaging, web page browsing, pictures management etc..
Application can be independently of what operating system provided, it is also possible to is that operating system carries.It addition, application 154 is installed to move
Time in dynamic terminal 100, it is also possible to add to operating system and drive module.
In above-mentioned various application 154, a kind of application therein is iris image perspective correction dress related to the present invention
Put 700.In certain embodiments, mobile terminal 100 is configured to perform the iris image perspective correction method according to the present invention
400。
When utilizing mobile terminal to carry out iris identification, it usually needs individually near-infrared photographic head carries out iris imaging,
(such as smart mobile phone is existing can not to carry out multiplexing with the photographic head of existing visual light imaging (spectral frequency is at 380-760nm)
The preposition colour imagery shot having), add the structure complexity of mobile terminal undoubtedly.And utilize mobile terminal single camera to carry out
The Compound scan technology of near infrared light and visible ray two waveband can effectively solve the problems referred to above.Fig. 2 shows according to the present invention one
The structured flowchart of the complex imaging system 200 of the mobile terminal 100 of individual embodiment.As in figure 2 it is shown, this complex imaging system bag
Include: this complex imaging system 200 includes lens assembly 230, optical filter box 220 and the image arranged successively along input path
Sensor 210.Wherein, optical filter box 220 includes visible band pass filter 221 and near infrared light bandpass filter 222 (figure
In be shown as filling with backslash), imageing sensor 210 includes that region A near infrared light imaging (is illustrated as with anti-
Oblique line fill), (be shown as filling out with horizontal line for the region B of visual light imaging and transitional region C between A, B region
Fill).
Full spectrum light line incidence is through lens assembly 230 and arrives optical filter box 220, wherein visible band pass filter
221 allow visible ray (such as, wavelength is 380-760nm) to pass through, and near infrared light bandpass filter 222 allows near infrared light
(such as, wavelength is 780-880nm) passes through.Visible band pass filter 221 and near infrared light bandpass filter 222 can pass through
Plated film realizes.By the visible ray of visible band pass filter 221 substantially in the region B imaging of imageing sensor, and pass through
The near infrared light of near infrared light bandpass filter 222 is substantially in the region A imaging of imageing sensor.Utilize the image processing software can
To be separated the imaging area of region B and A of imageing sensor respectively, wherein the imaging of region B corresponds to normal visible ray
Imaging when imaging, such as user use the mobile terminals such as such as mobile phone to carry out daily auto heterodyne, and the imaging of region A is corresponding near
Imaging under infrared mode, the such as user imaging when using mobile phone to carry out iris identification.As such, it is possible to realization can easily
See the switching between light and near infrared light imaging, switch optical filter without being equipped with moving component, be greatly improved steady
Qualitative.
Fig. 3 shows use mobile terminal collection auto heterodyne image and the schematic diagram of iris identification image.As it is shown on figure 3, use
Family is when autodyning, and the screen of mobile terminal is parallel with face, it can be observed that the auto heterodyne preview screen of full screen is (such as lower left corner figure
Show).And when carrying out iris identification, mobile terminal is tilted an angle, θ by user, in order to observe the iris being positioned at screen top
Identify preview screen (as the lower right corner illustrates).
Alternatively, it is also possible to the screen of holding mobile terminal is constant, the horizontal direction rotation in time autodyning of the direction of visual lines of face
Turn θ angle.Because both iris identification situations, mobile terminal and the relativeness of human eye sight are really the same, so this
Both of which is unified to be latter by invention, is the one-tenth under different sight angle of the human eye iris shown in Fig. 4
Image position and display position, in order to calculate.When human eye sight is not orthogonal to display screen, iris identification picture can produce
Deformation, affects the algorithm of iris identification, this paper presents a kind of by estimating that the angle of inclination of mobile terminal carries out rainbow for this
The method of film image perspective correction.
As shown in Figure 4, iris being regarded a disc as, the plane defining its place is object plane.Ignore eyeball radius pair
The impact of the iris depth of field, with the position of the positional representation iris of the eyeball centre of sphere.In order to make red at imageing sensor of human eye iris
Outer smooth regional imaging, in the range of need to ensureing the angle of visual field that eyeball is positioned at infrared light region.In order to make iris image clear, need to ensure
Eyeball is positioned at field depth.
Using right-handed coordinate system, if world coordinate system is with the intersection point of object plane and optical axis as initial point, x-axis forward is carried on the back from paper
Sensing front, face, y-axis forward is downward, and z-axis forward is to the right.Camera coordinate system is former with the camera lens center of mobile terminal
Point, x-axis forward is from sensing front, the paper back side, and y-axis forward is downward, and z-axis forward is to the right.Sensor coordinate system image taking sensor
Center be initial point, x-axis forward is from sensing front, the paper back side, and y-axis forward is downward, and z-axis forward is to the right.Coordinate system rotates to be used
Xyz Eulerian angles represent, i.e. first rotate around x-axis, rotate further around new y-axis, rotate further around new z-axis.The positive direction of the anglec of rotation
Defining by right hand rule, the counter clockwise direction i.e. looked against coordinate axes is positive-angle.
From the above description, it can be seen that object plane, image plane and image manifesting planes are world coordinate system, camera coordinates respectively
System and the X/Y plane of sensor coordinate system.When object plane is parallel with image plane, the profile of iris image is circular.But because
In actual iris identification operation, object plane and image plane are the most not parallel, and the profile causing the iris image finally obtained is ellipse
Circular.
In Fig. 4, the initial direction of visual lines of human eye is horizontal direction, shown in vector LOS0；During iris identification, user in order to
Observing iris image shown above the screen of mobile terminal, direction of visual lines is adjusted to LOS1, i.e. object plane is to have a look at
The x direction of ball center is that rotary shaft turns clockwise θ angle.The present invention is in rotary course, it is ensured that the depth of field of eyeball with become image position
Put constant.Correspondingly, the Y-axis of former world coordinate system has also turned clockwise θ angle along X-axis.Wherein set sight line during iris identification
Angle between the Y-axis of direction LOS1 and former world coordinate system is α, and the angle between the Y-axis of the world coordinate system rotated through
For β, it is known that, β=π-θ-α.
If should be appreciated that, holding human eye sight direction is constant, mobile terminal edge is deviated from human eye direction and rotates θ angle, then exist
In this case world coordinate system is unchanged, but the X/Y plane of camera coordinates system and sensor coordinate system have rotated θ angle around X-axis.But
Because under right hand rule, camera coordinate system have rotated θ angle relative to world coordinate system, be equivalent to world coordinate system relative to
Camera coordinate system have rotated-θ.So can be equivalent to keep camera coordinates system and sensor coordinate system constant, world coordinates
The X/Y plane of system rotates-θ angle around X-axis.This situation still can use the iris position shown in Fig. 4, image space, display
Position and the positional representation of world coordinate system.
As shown in Figure 4, if object distance is u, image distance is v, and the central point of imageing sensor mid-infrared imaging region to image passes
The distance of sensor central point is h.According to pinhole imaging system principle, H=h u/v.Separately set the central point of human eye iris to incident light axis
Distance be H, in the screen of mobile terminal, image display area is a to the distance of image sensor center point, in human eye iris
The heart is d with the distance at camera lens center.When carrying out distance and calculating, can according to eyes location algorithm from imaging region really
Determine position of human eye, and its position coordinates is scaled long measure from pixel unit.
According to above parameter, can be calculated the angle changing between human eye sight LOS0 and sight line LOS1 is:
Furthermore it is also possible to obtaining iris imaging light LOS1 with the angle of Y-axis in former world coordinate system is α=arctan
(u/H) the angle β=π-θ-α=π-θ-arctan of Y-axis, and in iris imaging light LOS1 and postrotational world coordinate system
(u/H)。
As described above, the photographing unit anglec of rotation is θx=0, θy=0, θz=0, can structure according to the photographing unit anglec of rotation
Make spin matrix R.Owing to not rotating, R is unit matrix.
And the photographing unit anglec of rotation is θ during iris identificationx'=θ, θy'=0, θz'=0, can according to the photographing unit anglec of rotation
Structure spin matrix
It addition, camera center OcCoordinate at former world coordinate system is cx=0, cy=0, cz=-u, is expressed as vector c
=[cx,cy,cz]T, wherein, T is matrix transpose.Camera center O during iris identificationcThe coordinate of world coordinate system after rotation
For c'x=0, c'y=H+dcos β, c'z=-dsin β, is expressed as vector c'=[cx',cy',cz']T。
For camera lens, it is known that its focal length is f, calibrated photographing unit matrix is C.Succinct for describing, photographing unit square
Battle array, through coefficient adjustment, makes the pixel unit after conversion become long measure.
According to an embodiment, Ke YiquWhich includes the focal length (f of both directionx, fy) and
Photocentre coordinate (cx, cy).Need to be multiplied by unit conversion factor carrying out Conversion of measurement unit, also need during practical operation to consider some non-thread
Property distortion.
Should be appreciated that iris coordinate and its image coordinate are the relations of perspective projection.1 p of known spatialw=[xw,yw,
zw]TCoordinate p under camera coordinate systemc=[xc,yc,zc]TFor pc=R (pw-c), the coordinate under sensor coordinate system
For ps=C pc, the form after being normalized the degree of depth isI.e. by this point of loss on iris image
Depth information
It is thus known that the iris image after existing deformation, can be according to space a little in world coordinate system, camera coordinates
Corresponding relation under system and sensor coordinate system infers undeformed iris image coordinate.Specifically, can be according to original rainbow
Film image is first in the coordinate system subinverse perspective projection rotated, then perspective projection under the coordinate system not rotated, can correction chart picture
Deformation.
Wherein, sitting against perspective projection process, the three dimensions first obtaining current deformation pattern according to the coordinate system rotated
Mark ps＇.Iris region is regarded as plane, utilizes according to anglec of rotation θ and object distance u, the deep of iris region every bit can be estimated
Degree informationGenerate with the coordinate under the sensor coordinate system of depth informationAfterwards, can basis
Sensor coordinate system recovers human eye iris coordinate p under camera coordinate system with the variation relation of camera coordinates systemc'=C- 1ps'.Then human eye iris seat under former world coordinate system is tried to achieve according to the transformation relation of camera coordinates system Yu world coordinate system
Mark pw=(R')-1pc'+c'。
Afterwards, under the coordinate system not rotated, perspective projection process is carried out, i.e. according to the coordinate p under former world coordinate systemw
Release the coordinate p under camera coordinates systemc=R (pw-c), then release the coordinate under sensor, the iris after being corrected
The three dimensional space coordinate p of images=CR [(R ＇)-1C-1ps＇+c ＇-c].
Fig. 5 shows the flow chart of iris image perspective correction method 500 according to an embodiment of the invention.Such as Fig. 5
Shown in, the method starts from step S510.
Subsequently, in step S510, gather face iris image to be identified.Iris image for collecting would generally
Carry out some pretreatment, to improve its precision and definition, as being normalized or noise reduction process etc..
Subsequently, in step S520, calculate the three dimensional space coordinate p of every bit in original iris images＇.Specifically,Wherein,It is the depth information of every bit in original iris image, is suitable to according to the anglec of rotation
Degree θ and object distance u are calculated.Wherein it is possible to determine position of human eye from imaging region according to eyes location algorithm, and by its position
Put coordinate and be scaled long measure from pixel unit, in order to coordinate calculates.
Subsequently, in step S530, obtain original according to the positional information calculation of human eye iris and original iris image thereof
The direction of visual lines of human eye and the angle theta of horizontal direction during iris image.Specifically,
Subsequently, in step S540, build the transformation matrix of iris image perspective correction according to angle, θ.Wherein, also include
Camera lens and the spin matrix R and R ＇ of former world coordinate system is built, if the initial point of former world coordinate system is according to described angle, θ
Incident light axis and the intersection point of human eye iris place plane, and have two coordinate axess to lay respectively at gravity and horizontal direction.
Specifically, R is unit matrix,
Subsequently, in step S550, according to the described transformation matrix three dimensional space coordinate p to original iris images＇ is carried out
Coordinate transform, the three dimensional space coordinate p of the iris image after being correcteds.Specifically, ps=CR [(R ＇)-1C-1ps＇+c ＇-c],
Wherein, C is the camera matrix through coefficient adjustment, is suitable to the pixel unit in image is converted to long measure；C and c ＇ is respectively
It is that the optical center of camera is relative to former world coordinate system and the world coordinate system coordinate rotated through.
Wherein, c=[cx,cy,cz]T, c ＇=[cx＇, cy＇, cz＇]T, wherein, T is matrix transpose, c and c ＇ is suitable to by folder
Angle θ, object distance u and the central point of human eye iris are calculated with distance H of incident light axis.
According to the calculating in Fig. 4, cx=cy=0, cz=-u, cx＇=0,
Finally, the long measure in coordinate is scaled pixel unit, and the iris image that remaps, iris can be taken turns
Exterior feature is corrected to circle from ellipse.Fig. 6 A and 6B respectively illustrates before and after carrying out perspective correction according to an embodiment of the invention
Image schematic diagram.It can be seen that before perspective correction, image is oval, and after carrying out perspective correction, image becomes round
Shape, hence it is evident that be beneficial to follow-up identification process.
Fig. 7 shows the structured flowchart of iris image perspective correction device 700 according to an embodiment of the invention.Such as figure
Shown in 7, this device includes: image acquisition unit 710, coordinate calculating unit 720, angle calculation unit 730, matrix construction unit
740 and coordinate transformation unit 750.
Image acquisition unit 710 is suitable to obtain the original iris image of user to be identified.
Coordinate calculating unit 720 is suitable to calculate the three dimensional space coordinate p of every bit in original iris images＇.
Angle calculation unit 730 is suitable to the positional information calculation according to described human eye iris and original iris image thereof and obtains
The direction of visual lines of human eye and the angle theta of horizontal direction during original iris image.
Matrix construction unit 740 is suitable to build the conversion square of described iris image perspective correction according to described anglec of rotation θ
Battle array.Wherein, also include building camera lens and the spin matrix R and R ＇ of former world coordinate system according to anglec of rotation θ.
Coordinate transformation unit, is suitable to the three dimensional space coordinate p according to described transformation matrix and original iris images＇ pair
Described original iris image carries out coordinate transform, the three dimensional space coordinate p of the iris image after being correcteds。
According to an embodiment, it is also possible to include unit conversion unit, be suitable to according to eyes location algorithm from imaging region
In determine position of human eye, and its position coordinates is scaled long measure from pixel unit；And by the iris after described correction
Long measure in image coordinate is scaled pixel unit, and the iris image that remaps.
Iris image perspective correction device 700 according to the present invention, its detail, the calculating of the most each parameter
Journey, detailed disclosure in description based on Fig. 1-Fig. 6, does not repeats them here.
As can be seen here, the present invention, by the iris region in the infrared image of location, determines that human eye iris is at imageing sensor
The image space of device, the display position on mobile terminal screen, and combine the human eye iris position of self, estimate acquisition rainbow
Mobile terminal and the angle in human eye sight direction during film image, this angle may be caused by the change of human eye sight direction, it is possible to
Can cause because of rotation of mobile terminal.Further, can confirm that the angle between imageing sensor and human eye iris, and according to this angle
Degree sets up the transformation matrix of iris image perspective transform.According to this transformation matrix, origin distortion iris image is converted, i.e.
First in the coordinate system subinverse perspective projection rotated, then perspective projection under the coordinate system not rotated, get final product correction chart distortion of image,
To approximating undistorted iris image.According to the solution of the present invention, can effectively eliminate human eye sight and be not orthogonal to screen time institute
The problem of the imaging distortion caused, is corrected to sub-circular by oval iris image, facilitates follow-up iris identification process,
Thus improve the accuracy of iris identification.
A8, method as described in A7, wherein, cx=cy=0, cz=-u, cx＇=0,
A9, method as described in A3, wherein, described camera matrixIncluding two change in coordinate axis direction
Focal length (fx, fy) and photocentre coordinate (cx, cy)。
A10, method as described in A1, also include: determine position of human eye from imaging region according to eyes location algorithm, and
Its position coordinates is scaled long measure from pixel unit；And by the length in the iris image coordinate after described correction
Unit conversion is pixel unit, and the iris image that remaps.
B12, device as described in B11, described matrix construction unit is further adapted for building described camera mirror according to described angle, θ
Head and the spin matrix R and R ＇ of former world coordinate system, wherein set the initial point of former world coordinate system as incident light axis and human eye iris
The intersection point of place plane, and have two coordinate axess to lay respectively at gravity and horizontal direction.
B13, device as described in B12, ps=CR [(R ＇)-1C-1ps＇+c ＇-c], wherein, C is the phase through coefficient adjustment
Machine matrix, is suitable to the pixel unit in image is converted to long measure；C and c ＇ is that the optical center of camera is relative to former respectively
World coordinate system and the coordinate of the former world coordinate system new coordinate system behind the axle rotation θ angle of non-gravity and horizontal direction.
B14, device as described in B11,Wherein,It is each in original iris image
The depth information of point, is suitable to be calculated according to anglec of rotation θ and object distance u.
B15, device as described in B12, wherein,
R is unit matrix,
B16, device as described in B11, the computing formula of described angle, θ is:
Wherein, u is object distance, and v is image distance, and h is that the central point of imageing sensor mid-infrared imaging region passes to described image
The distance of sensor central point, H is the central point distance to described incident light axis of described human eye iris, and a is described mobile terminal
Screen in image display area to the distance of described image sensor center point.
B17, device as described in B13, c=[cx,cy,cz]T, c ＇=[cx＇, cy＇, cz＇]T, wherein, T is matrix transpose, c
Distance H being suitable to the central point by angle theta, object distance u and human eye iris and incident light axis with c ＇ is calculated.
B18, method as described in B17, wherein, cx=cy=0, cz=-u, cx＇=0,
B19, device as described in B13, wherein, described camera matrixIncluding two coordinate axes sides
To focal length (fx, fy) and photocentre coordinate (cx, cy)。
B20, device as described in B11, also include: unit conversion unit, be suitable to according to eyes location algorithm from imaging area
Territory determines position of human eye, and its position coordinates is scaled long measure from pixel unit；And by the rainbow after described correction
Long measure in film image coordinate is scaled pixel unit, and the iris image that remaps.
Should be appreciated that one or more, the most right in order to simplify that the disclosure helping understands in each inventive aspect
In the description of the exemplary embodiment of the present invention, each feature of the present invention be sometimes grouped together into single embodiment, figure or
In person's descriptions thereof.But, should not be construed to the method for the disclosure reflect an intention that the most required for protection is sent out
The bright feature more features requiring ratio to be expressly recited in each claim.More precisely, as the following claims
As book is reflected, inventive aspect is all features less than single embodiment disclosed above.Therefore, it then follows specifically real
The claims executing mode are thus expressly incorporated in this detailed description of the invention, and the most each claim itself is as this
Bright independent embodiment.
Those skilled in the art are to be understood that the module of the equipment in example disclosed herein or unit or group
Part can be arranged in equipment as depicted in this embodiment, or alternatively can be positioned at and the equipment in this example
In different one or more equipment.Module in aforementioned exemplary can be combined as a module or be segmented into multiple in addition
Submodule.
Those skilled in the art are appreciated that and can carry out the module in the equipment in embodiment adaptively
Change and they are arranged in one or more equipment different from this embodiment.Can be the module in embodiment or list
Unit or assembly are combined into a module or unit or assembly, and can put them in addition multiple submodule or subelement or
Sub-component.In addition at least some in such feature and/or process or unit excludes each other, can use any
Combine all features disclosed in this specification (including adjoint claim, summary and accompanying drawing) and so disclosed appoint
Where method or all processes of equipment or unit are combined.Unless expressly stated otherwise, this specification (includes adjoint power
Profit require, summary and accompanying drawing) disclosed in each feature can by provide identical, equivalent or similar purpose alternative features come
Replace.
Although additionally, it will be appreciated by those of skill in the art that embodiments more described herein include other embodiments
Some feature included by rather than further feature, but the combination of the feature of different embodiment means to be in the present invention's
Within the scope of and form different embodiments.Such as, in the following claims, embodiment required for protection appoint
One of meaning can mode use in any combination.
Additionally, some in described embodiment be described as at this can be by the processor of computer system or by performing
The method of other device enforcement of described function or the combination of method element.Therefore, have for implementing described method or method
The processor of the necessary instruction of element is formed for implementing the method or the device of method element.Additionally, device embodiment
This described element is the example of following device: this device is for implementing by performed by the element of the purpose in order to implement this invention
Function.
As used in this, unless specifically stated so, ordinal number " first ", " second ", " the 3rd " etc. is used
Describe plain objects and be merely representative of the different instances relating to similar object, and be not intended to imply that the object being so described must
Must have the time upper, spatially, sequence aspect or in any other manner to definite sequence.
Although the embodiment according to limited quantity describes the present invention, but benefits from above description, the art
In it is clear for the skilled person that in the scope of the present invention thus described, it can be envisaged that other embodiments.Additionally, it should be noted that
The language that uses in this specification primarily to the readable and purpose of teaching and select rather than in order to explain or limit
Determine subject of the present invention and select.Therefore, in the case of without departing from the scope of the appended claims and spirit, for this
For the those of ordinary skill of technical field, many modifications and changes will be apparent from.For the scope of the present invention, to this
The disclosure that invention is done is illustrative and not restrictive, and it is intended that the scope of the present invention be defined by the claims appended hereto.
Claims (10)
1. an iris image perspective correction method, is suitable to performing in the terminal, and the method includes:
Obtain the original iris image of user to be identified；
Calculate the three dimensional space coordinate p of every bit in described original iris images＇；
When positional information calculation according to described human eye iris and original iris image thereof obtains original iris image, human eye regards
Line direction and the angle theta of horizontal direction；
The transformation matrix of described iris image perspective correction is built according to described angle, θ；
The three dimensional space coordinate p to described original iris image according to described transformation matrix and original iris images＇ sits
Mark conversion, the three dimensional space coordinate p of the iris image after being correcteds。
2. the method for claim 1, the step of the transformation matrix of described structure iris image perspective correction also includes:
Build described camera lens and the spin matrix R and R ＇ of former world coordinate system according to described angle, θ, wherein set the former world and sit
The intersection point that initial point is incident light axis and human eye iris place plane of mark system, and have two coordinate axess to lay respectively at gravity and level
Direction.
3. method as claimed in claim 2, ps=CR [(R ＇)-1C-1ps＇+c ＇-c],
Wherein, C is the camera matrix through coefficient adjustment, is suitable to the pixel unit in image is converted to long measure；C and c ＇
It is that the optical center of camera is revolved around the axle of non-gravity and horizontal direction relative to former world coordinate system and former world coordinate system respectively
Turn the coordinate of the new coordinate system behind θ angle.
4. the method for claim 1,
Wherein,It is the depth information of every bit in original iris image, is suitable to be calculated according to anglec of rotation θ and object distance u.
5. method as claimed in claim 2, wherein,
R is unit matrix,
6. the method for claim 1, the computing formula of described angle, θ is:
Wherein, u is object distance, and v is image distance, and h is that the central point of imageing sensor mid-infrared imaging region is to described imageing sensor
The distance of central point, H is the central point distance to described incident light axis of described human eye iris, and a is the screen of described mobile terminal
In Mu, image display area is to the distance of described image sensor center point.
7. method as claimed in claim 3, c=[cx,cy,cz]T, c ＇=[cx＇, cy＇, cz＇]T, wherein, T is matrix transpose, c
Distance H being suitable to the central point by angle theta, object distance u and human eye iris and incident light axis with c ＇ is calculated.
8. an iris image perspective correction device, be suitable to resident in the terminal, this device includes:
Image acquisition unit, is suitable to obtain the original iris image of user to be identified；
Coordinate calculating unit, is suitable to calculate the three dimensional space coordinate p of every bit in described original iris images＇；
Angle calculation unit, is suitable to the positional information calculation according to described human eye iris and original iris image thereof and obtains original rainbow
The direction of visual lines of human eye and the angle theta of horizontal direction during film image；
Matrix construction unit, is suitable to build the transformation matrix of described iris image perspective correction according to described angle, θ；
Coordinate transformation unit, is suitable to according to the described transformation matrix three dimensional space coordinate p to original iris images＇ carries out coordinate change
Change, the three dimensional space coordinate p of the iris image after being correcteds。
9. a mobile terminal, including iris image perspective correction device as claimed in claim 8.
10. mobile terminal as claimed in claim 9, also includes that couple mutually with described iris image perspective correction device is combined
Imaging system, this complex imaging system includes:
Lens assembly, including the optical lens of fixed focal length；
Optical filter box, including the visible band pass filter allowing the light of visible light wave range to pass through and permission near infrared light wave band
The near infrared light bandpass region passed through；And
Imageing sensor, including the transition region between visual light imaging region, near infrared light imaging region and the two region
Territory,
Wherein, described visual light imaging region under described visual light imaging pattern to by described visible band pass filter
Visible ray carries out imaging, and described near infrared light imaging region under described near infrared light imaging pattern to by described the reddest
The near infrared light of outer smooth bandpass filter carries out imaging.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610602917.8A CN106250839B (en) | 2016-07-27 | 2016-07-27 | A kind of iris image perspective correction method, apparatus and mobile terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610602917.8A CN106250839B (en) | 2016-07-27 | 2016-07-27 | A kind of iris image perspective correction method, apparatus and mobile terminal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106250839A true CN106250839A (en) | 2016-12-21 |
| CN106250839B CN106250839B (en) | 2019-06-04 |
Family
ID=57604365
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610602917.8A Active CN106250839B (en) | 2016-07-27 | 2016-07-27 | A kind of iris image perspective correction method, apparatus and mobile terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106250839B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107194968A (en) * | 2017-05-18 | 2017-09-22 | 腾讯科技（上海）有限公司 | Recognition and tracking method, device, intelligent terminal and the readable storage medium storing program for executing of image |
| CN107564089A (en) * | 2017-08-10 | 2018-01-09 | 腾讯科技（深圳）有限公司 | Three dimensional image processing method, device, storage medium and computer equipment |
| CN108765301A (en) * | 2018-03-27 | 2018-11-06 | 长春理工大学 | A kind of optical system and its distortion correction method and system |
| CN108875526A (en) * | 2018-01-05 | 2018-11-23 | 北京旷视科技有限公司 | Method, apparatus, system and the computer storage medium of line-of-sight detection |
| CN109726694A (en) * | 2019-01-02 | 2019-05-07 | 上海百豪新材料有限公司 | A kind of iris image acquiring method and device |
| CN110544285A (en) * | 2019-10-30 | 2019-12-06 | 南京安科医疗科技有限公司 | method and system for correcting head position in head CT image |
| CN111145087A (en) * | 2019-12-30 | 2020-05-12 | 维沃移动通信有限公司 | Image processing method and electronic equipment |
| CN111144219A (en) * | 2019-11-29 | 2020-05-12 | 武汉虹识技术有限公司 | Iris recognition device and method based on 3D structured light |
| CN111428654A (en) * | 2020-03-27 | 2020-07-17 | 北京万里红科技股份有限公司 | Iris identification method, device and storage medium |
| CN112417951A (en) * | 2020-09-30 | 2021-02-26 | 北京极豪科技有限公司 | Fingerprint image calibration method and device, electronic equipment and storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060165266A1 (en) * | 2005-01-26 | 2006-07-27 | Honeywell International Inc. | Iris recognition system and method |
| CN201307266Y (en) * | 2008-06-25 | 2009-09-09 | 韩旭 | Binocular sightline tracking device |
| CN101656840A (en) * | 2008-08-22 | 2010-02-24 | 原相科技股份有限公司 | Wide-angle sensor array module and image correcting method, operating method and application thereof |
| CN103870796A (en) * | 2012-12-13 | 2014-06-18 | 汉王科技股份有限公司 | Eye sight evaluation method and device |
| CN104484649A (en) * | 2014-11-27 | 2015-04-01 | 北京天诚盛业科技有限公司 | Method and device for identifying irises |
| CN204270321U (en) * | 2014-12-24 | 2015-04-15 | 武汉虹识技术有限公司 | A kind of iris collection device |
| CN104615978A (en) * | 2015-01-23 | 2015-05-13 | 清华大学 | Sight direction tracking method and device |
| CN105094337A (en) * | 2015-08-19 | 2015-11-25 | 华南理工大学 | Three-dimensional gaze estimation method based on irises and pupils |
| CN105187726A (en) * | 2015-06-17 | 2015-12-23 | 广州市巽腾信息科技有限公司 | Multifunctional mobile image processing device, processing method of utilizing multifunctional mobile image processing device, and use of multifunctional mobile image processing device |
| CN105740846A (en) * | 2016-03-02 | 2016-07-06 | 河海大学常州校区 | Horizontal visual angle estimation and calibration method based on depth camera |
-
2016
- 2016-07-27 CN CN201610602917.8A patent/CN106250839B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060165266A1 (en) * | 2005-01-26 | 2006-07-27 | Honeywell International Inc. | Iris recognition system and method |
| CN201307266Y (en) * | 2008-06-25 | 2009-09-09 | 韩旭 | Binocular sightline tracking device |
| CN101656840A (en) * | 2008-08-22 | 2010-02-24 | 原相科技股份有限公司 | Wide-angle sensor array module and image correcting method, operating method and application thereof |
| CN103870796A (en) * | 2012-12-13 | 2014-06-18 | 汉王科技股份有限公司 | Eye sight evaluation method and device |
| CN104484649A (en) * | 2014-11-27 | 2015-04-01 | 北京天诚盛业科技有限公司 | Method and device for identifying irises |
| CN204270321U (en) * | 2014-12-24 | 2015-04-15 | 武汉虹识技术有限公司 | A kind of iris collection device |
| CN104615978A (en) * | 2015-01-23 | 2015-05-13 | 清华大学 | Sight direction tracking method and device |
| CN105187726A (en) * | 2015-06-17 | 2015-12-23 | 广州市巽腾信息科技有限公司 | Multifunctional mobile image processing device, processing method of utilizing multifunctional mobile image processing device, and use of multifunctional mobile image processing device |
| CN105094337A (en) * | 2015-08-19 | 2015-11-25 | 华南理工大学 | Three-dimensional gaze estimation method based on irises and pupils |
| CN105740846A (en) * | 2016-03-02 | 2016-07-06 | 河海大学常州校区 | Horizontal visual angle estimation and calibration method based on depth camera |
Non-Patent Citations (1)
| Title |
|---|
| 温晴川: "基于双目立体视觉的视线跟踪系统标定", 《光学学报》 * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107194968A (en) * | 2017-05-18 | 2017-09-22 | 腾讯科技（上海）有限公司 | Recognition and tracking method, device, intelligent terminal and the readable storage medium storing program for executing of image |
| CN107194968B (en) * | 2017-05-18 | 2024-01-16 | 腾讯科技（上海）有限公司 | Image identification tracking method and device, intelligent terminal and readable storage medium |
| CN107564089A (en) * | 2017-08-10 | 2018-01-09 | 腾讯科技（深圳）有限公司 | Three dimensional image processing method, device, storage medium and computer equipment |
| CN108875526A (en) * | 2018-01-05 | 2018-11-23 | 北京旷视科技有限公司 | Method, apparatus, system and the computer storage medium of line-of-sight detection |
| CN108765301A (en) * | 2018-03-27 | 2018-11-06 | 长春理工大学 | A kind of optical system and its distortion correction method and system |
| CN108765301B (en) * | 2018-03-27 | 2020-08-07 | 长春理工大学 | Optical system and distortion correction method and system thereof |
| CN109726694A (en) * | 2019-01-02 | 2019-05-07 | 上海百豪新材料有限公司 | A kind of iris image acquiring method and device |
| CN109726694B (en) * | 2019-01-02 | 2023-08-25 | 上海百豪新材料有限公司 | Iris image acquisition method and device |
| CN110544285A (en) * | 2019-10-30 | 2019-12-06 | 南京安科医疗科技有限公司 | method and system for correcting head position in head CT image |
| CN111144219A (en) * | 2019-11-29 | 2020-05-12 | 武汉虹识技术有限公司 | Iris recognition device and method based on 3D structured light |
| CN111144219B (en) * | 2019-11-29 | 2023-08-18 | 武汉虹识技术有限公司 | Iris recognition device and method based on 3D structured light |
| CN111145087B (en) * | 2019-12-30 | 2023-06-30 | 维沃移动通信有限公司 | Image processing method and electronic equipment |
| CN111145087A (en) * | 2019-12-30 | 2020-05-12 | 维沃移动通信有限公司 | Image processing method and electronic equipment |
| CN111428654A (en) * | 2020-03-27 | 2020-07-17 | 北京万里红科技股份有限公司 | Iris identification method, device and storage medium |
| CN111428654B (en) * | 2020-03-27 | 2023-11-28 | 北京万里红科技有限公司 | Iris recognition method, iris recognition device and storage medium |
| CN112417951B (en) * | 2020-09-30 | 2022-06-24 | 北京极豪科技有限公司 | Fingerprint image calibration method and device, electronic equipment and storage medium |
| CN112417951A (en) * | 2020-09-30 | 2021-02-26 | 北京极豪科技有限公司 | Fingerprint image calibration method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106250839B (en) | 2019-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106250839A (en) | A kind of iris image perspective correction method, device and mobile terminal | |
| Grossberg et al. | The raxel imaging model and ray-based calibration | |
| US20160019421A1 (en) | Multispectral eye analysis for identity authentication | |
| WO2017082100A1 (en) | Authentication device and authentication method employing biometric information | |
| US20170076430A1 (en) | Image Processing Method and Image Processing Apparatus | |
| US20160019420A1 (en) | Multispectral eye analysis for identity authentication | |
| US20170091550A1 (en) | Multispectral eye analysis for identity authentication | |
| CN106295533A (en) | Optimization method, device and the camera terminal of a kind of image of autodyning | |
| US20120027266A1 (en) | Time-of-flight sensor-assisted iris capture system and method | |
| CA3023690A1 (en) | Fixtureless lensmeter and methods of operating same | |
| KR20170098089A (en) | Electronic apparatus and operating method thereof | |
| CN106999038A (en) | Message processing device, information processing method and program | |
| CN106529436A (en) | Identity consistency authentication method and device, and mobile terminal | |
| US20230080861A1 (en) | Automatic Iris Capturing Method And Apparatus, Computer-Readable Storage Medium, And Computer Device | |
| US20200393896A1 (en) | System and method for gaze estimation | |
| CN104205825B (en) | Image processing apparatus and method and camera head | |
| WO2020018338A1 (en) | Image acquisition method, apparatus, system, device and medium | |
| CN106155515A (en) | The method of adjustment of screen display direction and device | |
| CN107392088A (en) | Three-dimensional vein identification device and method, switch, mobile terminal | |
| CN109389018A (en) | A kind of facial angle recognition methods, device and equipment | |
| EP3255878B1 (en) | Electronic device and control method therefor | |
| EP3300352B1 (en) | Method and electronic device for detecting wavelength spectrum of incident light | |
| JP7282884B2 (en) | Three-dimensional authentication device, three-dimensional authentication system, portable information terminal, and three-dimensional authentication method | |
| CN107659772A (en) | 3D rendering generation method, device and electronic equipment | |
| CN106254752B (en) | Focusing method and device, image capture device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information |
Inventor after: Wang Xiaopeng Inventor before: Wang Xiaopeng Inventor before: Guo Yansong |
|
| CB03 | Change of inventor or designer information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |